{"title":"Machine learning (ML)-based lithography optimizations","authors":"Seongbo Shim, Suhyeong Choi, Youngsoo Shin","doi":"10.1109/APCCAS.2016.7804021","DOIUrl":null,"url":null,"abstract":"Recent lithography optimizations demand higher accuracy and cause longer runtime. Optical proximity correction (OPC) and sub-resolution assist feature (SRAF) insertion, for example, take a few days due to lengthy lithography simulations and high pattern density. Etch proximity correction (EPC) is another example of intensive optimization due to a complex physical model of etching process. Machine learning has recently been applied to these lithography optimizations with some success. In this paper, we introduce basic algorithms of machine learning technique, e.g. support vector machine (SVM) and neural networks, and how they are applied to lithography optimization problems. Discussion on learning parameters, preparation of compact learning data set, technique to avoid over-fitting are also provided.","PeriodicalId":6495,"journal":{"name":"2016 IEEE Asia Pacific Conference on Circuits and Systems (APCCAS)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"8","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2016 IEEE Asia Pacific Conference on Circuits and Systems (APCCAS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/APCCAS.2016.7804021","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 8
Abstract
Recent lithography optimizations demand higher accuracy and cause longer runtime. Optical proximity correction (OPC) and sub-resolution assist feature (SRAF) insertion, for example, take a few days due to lengthy lithography simulations and high pattern density. Etch proximity correction (EPC) is another example of intensive optimization due to a complex physical model of etching process. Machine learning has recently been applied to these lithography optimizations with some success. In this paper, we introduce basic algorithms of machine learning technique, e.g. support vector machine (SVM) and neural networks, and how they are applied to lithography optimization problems. Discussion on learning parameters, preparation of compact learning data set, technique to avoid over-fitting are also provided.